Due to the class-imbalance and redundancy of sample features, the network intrusion detection model based on classification algorithm has high false positive rate (FPR) for minority sample. A network intrusion detecti...
详细信息
ISBN:
(纸本)9781450389099
Due to the class-imbalance and redundancy of sample features, the network intrusion detection model based on classification algorithm has high false positive rate (FPR) for minority sample. A network intrusion detection model based on pca + ADASYN and XGBoost is proposed. The principal component analysis (pca) algorithm is used to reduce the redundancy features of the data. On this basis, the adaptive synthetic sampling (ADASYN) algorithm is used to oversample minority sample to solve the problem of class-imbalanced at the data level. Finally, XGBoost is used as a classifier to classify the detected data. In order to verify the validity of the model, several groups of comparative experiments were carried out on KDD CUP99 data set. The FPR of the proposed model for minority samples (r2l, u2r) were 17.3% and 19.7%, and the F1 were 90.1% and 84.5%. The experimental results show that by dealing with the problem of data redundancy and class-imbalanced, we can reduce the FPR of the detection model for minority sample and improve the F1.
The Principal Component Analysis (pca) algorithm is widely used in the field of face recognition because of its high recognition rate and simplicity. The pca algorithm is based on the principle of Karhunen-Loeve Trans...
详细信息
ISBN:
(纸本)9781450361910
The Principal Component Analysis (pca) algorithm is widely used in the field of face recognition because of its high recognition rate and simplicity. The pca algorithm is based on the principle of Karhunen-Loeve Transformation, because the pca algorithm is sensitive to outliers, it is improved on the basis of pca algorithm, combined with Linear Discriminant Analysis (LDA) algorithm, the pca-LDA face recognition method is proposed. This method obtains the feature space of training sample set by pca algorithm, On this basis, the LDA algorithm is executed to obtain the feature space of fusion. The pca is then fused with the LDA's feature space to obtain the new feature space that combines the two. Finally, the face projected in the new feature space is trained and recognized. The experimental results show that the face recognition algorithm proposed in this paper has a higher recognition rate than the traditional pca algorithm.
Unconstrained handwritten numeral recognition using self-organizing maps (SOM), and self-organizing principal component analysis (pca) is presented in this paper. In the feature-extraction phase, we develop the method...
详细信息
ISBN:
(纸本)7505338900
Unconstrained handwritten numeral recognition using self-organizing maps (SOM), and self-organizing principal component analysis (pca) is presented in this paper. In the feature-extraction phase, we develop the methods to acquire nonlinear normalization of the numeral image. In the classifying phase, we construct the classifier by two layers: pca and SOM. To acquire the ability, of real-time self-learning, the algorithm of pca and SOM are combined together, just as their combination in structure. Experiments on 48000 handwritten numerals show that our technique achieves satisfactory results in terms of classification accuracy and time.
Tato bakalářská práce se věnuje realizaci a testování programového vybavení pro zpracování vícerozměrných dat ze senzorů plynů. Práce seznamuje čtenář...
详细信息
Tato bakalářská práce se věnuje realizaci a testování programového vybavení pro zpracování vícerozměrných dat ze senzorů plynů. Práce seznamuje čtenáře s některými metodami zpracování vícerozměrných dat. Součástí práce je popis a použití metody pca, popis zařízení určeného k detekci zápachů nebo chutí – elektronického nosu, realizace a testování programu pro předzpracování a zpracování dat. Program pro předzpracování dat je schopen zobrazovat data ze zařízení na grafu v reálném čase a uložit je do souboru. Program pro zpracování dat umožňuje nahrát data ze souboru, snížit jejich rozměrnost a zobrazit výsledky do 2D grafu. Tento program byl otestován na jednoduchém elektronickém nosu, který obsahuje tři senzory.
Electric energy is an indispensable energy in life, and the power network is the basis to ensure its normal circulation, in which the operation status of power equipment is one of the key factors to determine the safe...
详细信息
Electric energy is an indispensable energy in life, and the power network is the basis to ensure its normal circulation, in which the operation status of power equipment is one of the key factors to determine the safe and stable operation of the power network. In the information age, the traditional manual periodic inspection and the existing method of relying on manual monitoring equipment operation status can no longer meet the needs of safe operation of equipment;relying on computer technology and image recognition technology to achieve automatic identification of power equipment has become a research hot spot. In order to realize automatic identification of power equipment, this paper presents a method of recognition of power equipment based on image processing. Firstly, the power equipment image is preprocessed by various denoising and sharpening algorithms to remove the noise and distortion of the image and improve the image quality;secondly, the SIFT algorithm is used to extract image features, and pca algorithm is used to reduce the dimension;finally, the support vector machine is used to classify and recognize the image. The simulation results show that the proposed denoising and sharpening algorithms can process images well and improve the quality of images. The support vector machine is used to classify the image features processed by SIFT algorithm and pca algorithm, and the automatic recognition of power equipment is realized. And the method of power identification based on image processing proposed in this paper has good recognition accuracy.
Aim: Revision hip arthroplasty has a less favorable outcome than primary total hip arthroplasty and an understanding of the timing of total hip arthroplasty failure may be helpful. The aim of this study is to develop ...
详细信息
Aim: Revision hip arthroplasty has a less favorable outcome than primary total hip arthroplasty and an understanding of the timing of total hip arthroplasty failure may be helpful. The aim of this study is to develop a combined deep learning (DL) and machine learning (ML) approach to automatically detect hip prosthetic failure from conventional plain radiographs. Methods: Two cohorts of patients (of 280 and 352 patients) were included in the study, for model development and validation, respectively. The analysis was based on one antero-posterior and one lateral radiographic view obtained from each patient during routine post-surgery follow-up. After pre-processing, three images were obtained: the original image, the acetabulum image and the stem image. These images were analyzed through convolutional neural networks aiming to predict prosthesis failure. Deep features of the three images were extracted for each model and two feature-based pipelines were developed: one utilizing only the features of the original image (original image pipeline) and the other concatenating the features of the three images (3-image pipeline). The obtained features were either used directly or reduced through principal component analysis. Both support vector machine (SVM) and random forest (RF) classifiers were considered for each pipeline. Results: The SVM applied to the 3-image pipeline provided the best performance, with an accuracy of 0.958 +/- 0.006 in the internal validation and an F1-score of 0.874 in the external validation set. The explainability analysis, besides identifying the features of the complete original images as the major contributor, highlighted the role of the acetabulum and stem images on the prediction. Conclusions: This study demonstrated the potentialities of the developed DL-ML procedure based on plain radiographs in the detection of the failure of the hip prosthesis.
In order to improve the accuracy of the reform quality research and shorten the overall research time, the reform quality research is carried out based on the big data mining technology. First, the local density infor...
详细信息
In order to improve the accuracy of the reform quality research and shorten the overall research time, the reform quality research is carried out based on the big data mining technology. First, the local density information of the data is calculated and the required samples are mined. Secondly, the probabilistic undirected graph model is used to remove the noise in the mining samples and improve the accuracy of the sample data. Finally, the pca algorithm in big data is used to calculate the contribution rate of the sample data, and the reform evaluation model is constructed. The test results of different indicators show that the accuracy rate of the research method is 92.6%, and the evaluation time is only 12.7 s, which can effectively improve the evaluation accuracy and shorten the evaluation time.
In order to eliminate the shadows in vehicle detection,the accuracy of traffic monitoring is *** this text,the foreground object is extracted by background subtraction *** orientation of the shadow region is determine...
详细信息
In order to eliminate the shadows in vehicle detection,the accuracy of traffic monitoring is *** this text,the foreground object is extracted by background subtraction *** orientation of the shadow region is determined by the pca,which can reduce the complexity of *** shadow area is similar to background to weaken *** foreground is extracted again by the same method after weaken *** shadow area is transformed into the background and separated from the moving *** experimental results show the average value of three groups video of comprehensive indexes is obtained that the algorithm is improved by 10.3%and 13.3%compared with the color and edge based shadow elimination ***,the shadow detection and elimination algorithm work well and the performance is reliable.
暂无评论